ChengXiang Zhai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
ChengXiang Zhai has a total of 226 co-authors. Here are the top co-authors by number of shared publications:
- Heng Ji
University of Illinois Urbana-Champaign, USA
12 shared publications - Jiawei Han
University of Illinois Urbana-Champaign, Urbana, Illinois, USA
8 shared publications - Krisztian Balog
University of Stavanger, Stavanger, Norway
7 shared publications - Bhavya Bhavya
University of Illinois at Urbana-Champaign
5 shared publications - Chenkai Sun
University of Illinois Urbana-Champaign
5 shared publications - Kevin Ros
University of Illinois Urbana-Champaign, Urbana, IL, USA
5 shared publications
Latest Publications
- Open Access
- 19 October 2026
- Published by MDPI AG in Preprints.org
Native Real-Time Interactive Omni Intelligence: A Unified Framework
The rapid progress of large language models has established strong foundations for reasoning, knowledge, and generation, while the integration of vision, audio, video, and other modalities has extended these capabilities toward increasingly unified intelligence across modalities, which we refer to as Omni Intelligence. Yet, real-world assistants must do more than process completed multimodal prompts. They must perceive evolving streams, respond while new evidence is arriving, handle hesitation, overlap, interruption, and changing intent, and coordinate reasoning or tool use that may proceed asynchronously. We refer to this broader capability as \( \textbf{Interactive Omni Intelligence} \): the ability to maintain and exercise omni intelligence under the temporal and adaptive demands of real-time interaction. The question guiding this paper is: How can foundation-model capabilities be carried into real-time interaction while preserving both intelligence and interactivity?We develop a conceptual framework connecting two development paths. One adapts pretrained language or omni models through streaming interfaces, modality modules, post-training, and orchestration. The other develops model-native systems that learn temporal structure, continuous multimodal processing, generation, and interaction control. Across both paths, we compare representations, architectures, fusion, data, training objectives, serving, and evaluation. Their comparison reveals an Intelligence--Interactivity Trade-off between preserving reasoning and knowledge, and meeting the timing, coordination, and resource demands of continuous operation. We examine Multi-Rate Interactive Intelligence as a cross-cutting direction, including foreground--background designs that coordinate fast interaction with slower reasoning, retrieval, memory, and tools. Finally, we identify open problems in evolving state, persistent and proactive interaction, joint evaluation, and safe open-world operation. The resulting framework connects capability preservation, interaction control, and multi-rate coordination.- 19 October 2026
- Published by MDPI AG in Preprints.org
Open AccessNative Real-Time Interactive Omni Intelligence: A Unified Framework
The rapid progress of large language models has established strong foundations for reasoning, knowledge, and generation, while the integration of vision, audio, video, and other modalities has extended these capabilities toward increasingly unified intelligence across modalities, which we refer to as Omni Intelligence. Yet, real-world assistants must do more than process completed multimodal prompts. They must perceive evolving streams, respond while new evidence is arriving, handle hesitation, overlap, interruption, and changing intent, and coordinate reasoning or tool use that may proceed asynchronously. We refer to this broader capability as \( \textbf{Interactive Omni Intelligence} \): the ability to maintain and exercise omni intelligence under the temporal and adaptive demands of real-time interaction. The question guiding this paper is: How can foundation-model capabilities be carried into real-time interaction while preserving both intelligence and interactivity?We develop a conceptual framework connecting two development paths. One adapts pretrained language or omni models through streaming interfaces, modality modules, post-training, and orchestration. The other develops model-native systems that learn temporal structure, continuous multimodal processing, generation, and interaction control. Across both paths, we compare representations, architectures, fusion, data, training objectives, serving, and evaluation. Their comparison reveals an Intelligence--Interactivity Trade-off between preserving reasoning and knowledge, and meeting the timing, coordination, and resource demands of continuous operation. We examine Multi-Rate Interactive Intelligence as a cross-cutting direction, including foreground--background designs that coordinate fast interaction with slower reasoning, retrieval, memory, and tools. Finally, we identify open problems in evolving state, persistent and proactive interaction, joint evaluation, and safe open-world operation. The resulting framework connects capability preservation, interaction control, and multi-rate coordination. - Open Access
- 31 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
LOALab: Towards An Open AI Innovation Ecosystem for Unifying Research, Education, and Application Development
- 31 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessLOALab: Towards An Open AI Innovation Ecosystem for Unifying Research, Education, and Application Development
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2780-2789
Towards a General Intelligent Information Agent: Framework, Models, and Evaluation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2780-2789
Open AccessTowards a General Intelligent Information Agent: Framework, Models, and Evaluation
- Open Access
- 24 April 2026
- Published by Association for Computing Machinery (ACM) in Communications of the ACM
- Vol. 69 (5) , 45-48
The Indispensable Role of User Simulation in the Pursuit of AGI
Why user simulation research is crucial for making progress toward truly intelligent systems.
- 24 April 2026
- Published by Association for Computing Machinery (ACM) in Communications of the ACM
- Vol. 69 (5) , 45-48
Open AccessThe Indispensable Role of User Simulation in the Pursuit of AGI
Why user simulation research is crucial for making progress toward truly intelligent systems.
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
GCVAE: A graph conditional variational autoencoder for feature dependency guided synthetic metabolomic data generation
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessGCVAE: A graph conditional variational autoencoder for feature dependency guided synthetic metabolomic data generation
- Open Access
The Indispensable Role of User Simulation in the Pursuit of AGI
Progress toward Artificial General Intelligence (AGI) faces significant bottlenecks, particularly in rigorously evaluating complex interactive systems and acquiring the vast interaction data needed for training adaptive agents. This paper posits that user simulation -- creating computational agents that mimic human interaction with AI systems -- is not merely a useful tool, but is a critical catalyst required to overcome these bottlenecks and accelerate AGI development. We argue that realistic simulators provide the necessary environments for scalable evaluation, data generation for interactive learning, and fostering the adaptive capabilities central to AGI. Therefore, research into user simulation technology and intelligent task agents are deeply synergistic and must advance hand-in-hand. This article elaborates on the critical role of user simulation for AGI, explores the interdisciplinary nature of building realistic simulators, identifies key challenges including those posed by large language models, and proposes a future research agenda.
Open AccessThe Indispensable Role of User Simulation in the Pursuit of AGI
Progress toward Artificial General Intelligence (AGI) faces significant bottlenecks, particularly in rigorously evaluating complex interactive systems and acquiring the vast interaction data needed for training adaptive agents. This paper posits that user simulation -- creating computational agents that mimic human interaction with AI systems -- is not merely a useful tool, but is a critical catalyst required to overcome these bottlenecks and accelerate AGI development. We argue that realistic simulators provide the necessary environments for scalable evaluation, data generation for interactive learning, and fostering the adaptive capabilities central to AGI. Therefore, research into user simulation technology and intelligent task agents are deeply synergistic and must advance hand-in-hand. This article elaborates on the critical role of user simulation for AGI, explores the interdisciplinary nature of building realistic simulators, identifies key challenges including those posed by large language models, and proposes a future research agenda.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1388-1399
Learning to Slice: Self-Supervised Interpretable Hierarchical Representation Learning with Graph Auto-Encoder Tree
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1388-1399
Open AccessLearning to Slice: Self-Supervised Interpretable Hierarchical Representation Learning with Graph Auto-Encoder Tree
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4046-4050
InstInfo: A Just-in-Time Literature Recommendation System for Presentations
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4046-4050
Open AccessInstInfo: A Just-in-Time Literature Recommendation System for Presentations
- Top Cited PapersOpen Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4138-4141
Theory and Toolkits for User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4138-4141
Top Cited PapersOpen AccessTheory and Toolkits for User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4056-4060
TINK: Text Information Navigation Kit
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4056-4060
Open AccessTINK: Text Information Navigation Kit